Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 3037
    Prev
    Next
    INDEX
    Explanations

    elements related to identity and recognition of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lay
    -0.57
     ural
    -0.56
     disponibilités
    -0.54
    mamış
    -0.54
     getattr
    -0.54
    OCUS
    -0.53
    WebVitals
    -0.52
    ISupport
    -0.52
    ()))
    
    -0.52
    lück
    -0.51
    POSITIVE LOGITS
    ActionCreators
    0.65
     Catawiki
    0.62
    最快更新
    0.61
     tourne
    0.53
     entière
    0.52
    териалы
    0.51
    Spinach
    0.50
     autorytatywna
    0.50
     informée
    0.49
     fullt
    0.49
    Activations Density 0.327%

    No Known Activations